Commit Graph

298 Commits

Author SHA1 Message Date
James Ravenscroft
7bb93b6f4e fix docker build for tags 2023-08-26 17:01:35 +01:00
James Ravenscroft
2b27760a7f
Merge pull request #55 from ravenscroftj/feature/gpu_layers
WIP: Integrate more direct GPU support
2023-08-26 16:35:52 +01:00
James Ravenscroft
a00de2a332 recomment the cuda preprocessor check 2023-08-26 16:21:42 +01:00
James Ravenscroft
215a69b5af update clblast code in gpt-j model 2023-08-26 16:16:01 +01:00
James Ravenscroft
91639b8fc0 disable clblast docker images 2023-08-26 16:12:50 +01:00
James Ravenscroft
0b408510f4 add gpu offload for gpt-j models (codegen) 2023-08-26 16:11:16 +01:00
James Ravenscroft
604183380d tidy up prints in stablecoder and starcoder 2023-08-26 16:04:41 +01:00
James Ravenscroft
88683abe50 update run script to incorporate GPU layers 2023-08-26 16:03:16 +01:00
James Ravenscroft
326e76c9bb Merge branch 'main' into feature/gpu_layers 2023-08-26 15:59:13 +01:00
James Ravenscroft
23c0a3d19e Merge branch 'feature/gpu_layers' of github.com:ravenscroftj/turbopilot into feature/gpu_layers 2023-08-26 15:34:28 +01:00
James Ravenscroft
31bb33c731 use latest upstream ggml instead of mine 2023-08-26 15:34:15 +01:00
James Ravenscroft
d4989b543c
Merge pull request #62 from ravenscroftj/feature/blasdocker
Implement better docker builds
2023-08-26 15:32:13 +01:00
James Ravenscroft
e9dc6a304a use latest upstream ggml instead of mine 2023-08-26 15:22:14 +01:00
James Ravenscroft
97a0377cd6 remove llama.cpp submodule 2023-08-26 15:21:01 +01:00
James Ravenscroft
6d26c9b064 Merge branch 'feature/gpu_layers' of github.com:ravenscroftj/turbopilot into feature/gpu_layers 2023-08-26 15:20:25 +01:00
James Ravenscroft
63b554793d tidy cmakelist 2023-08-26 15:20:02 +01:00
James Ravenscroft
0cf7a9c341 remove llama 2023-08-26 15:19:51 +01:00
James Ravenscroft
356a83c5fd remove crow submodule 2023-08-26 15:19:17 +01:00
James Ravenscroft
a5517b0fcd use ggerganov ggml instead of mine 2023-08-26 15:19:04 +01:00
James Ravenscroft
8fa70e1518 update for gpu build 2023-08-26 15:14:18 +01:00
James Ravenscroft
b79ab46b50 add gpu offload for gptneox 2023-08-26 15:14:02 +01:00
James Ravenscroft
4a47251822 update for gpu build 2023-08-26 15:13:08 +01:00
James Ravenscroft
b2b4a1480f increase scratch on starcoder 2023-08-26 15:12:41 +01:00
James Ravenscroft
5f7155a314 add gpu offload for gptneox 2023-08-26 15:12:41 +01:00
James Ravenscroft
77cde95cb9 remove deprecated cuda dockerfiles 2023-08-26 14:17:31 +01:00
James Ravenscroft
bea7ebdb34 correct runtime libs for openblas and clblast 2023-08-26 14:16:39 +01:00
James Ravenscroft
812bbea9d7 correct typo with clblast 2023-08-26 13:53:26 +01:00
James Ravenscroft
08e8834390 add changes to dockerfile 2023-08-26 13:51:50 +01:00
James Ravenscroft
25680e64d8 remove all the quotes 2023-08-26 13:43:33 +01:00
James Ravenscroft
dca25d8456 remove quotes 2023-08-26 13:42:11 +01:00
James Ravenscroft
1f6f84a783 add quotes to args 2023-08-26 13:39:02 +01:00
James Ravenscroft
0183b30502 always use ubuntu 22.04 2023-08-26 13:32:01 +01:00
James Ravenscroft
b465eae818 break out vars 2023-08-26 13:28:08 +01:00
James Ravenscroft
e8adff5339 try again 2023-08-26 13:22:09 +01:00
James Ravenscroft
f12dacaa15 read the readme properly 2023-08-26 13:16:34 +01:00
James Ravenscroft
0b0b914f92 add commas? 2023-08-26 13:12:27 +01:00
James Ravenscroft
b21dd0799d fix basenames 2023-08-26 13:10:23 +01:00
James Ravenscroft
c73c196364 build nvidia with default dockerfile 2023-08-26 13:08:19 +01:00
James Ravenscroft
30834e3121 remove brew update to prevent python breaking build 2023-08-26 12:58:02 +01:00
James Ravenscroft
39c3182a3a try to fix build args 2023-08-26 12:57:00 +01:00
James Ravenscroft
2abdcabf02 use lists for build args 2023-08-26 12:45:23 +01:00
James Ravenscroft
6877542ad8 blas docker build 2023-08-26 12:43:52 +01:00
James Ravenscroft
5b561f7b7e
Merge pull request #61 from c01o/patch-1
Fix download link on MODELS.md
2023-08-26 12:37:21 +01:00
c01o
e85492d8ba
Fix download link on MODELS.md 2023-08-26 19:16:15 +09:00
James Ravenscroft
f840ea0b73
Merge pull request #60 from nvtienanh/update-dockerfile-default
Change from alpine to ubuntu in Dockerfile.default
2023-08-26 09:43:24 +01:00
Anh Nguyen
3e37c4bb7c Update cmake command 2023-08-26 14:27:27 +07:00
Anh Nguyen
20b1460bd8 Using GGML_STATIC 2023-08-26 14:21:18 +07:00
Anh Nguyen
2308b9ae21 Change from alpine to ubuntu in dockerfile.default 2023-08-26 13:21:04 +07:00
James Ravenscroft
c4e57e0aab
Merge pull request #58 from ravenscroftj/feature/model-lock
WIP: implement locking of model per request
2023-08-25 06:57:05 +01:00
James Ravenscroft
dc81abbc52 Merge branch 'main' into feature/model-lock 2023-08-24 14:58:44 +01:00